How to Use the Comet ML MCP in Pydantic AI

Q: What happens if Comet ML returns malformed metrics to Pydantic AI?

The framework fails loudly. If getexperimentmetrics returns data that violates your schema, Pydantic AI raises a validation error immediately.

Q: Can I use Pydantic AI validation with Comet ML workspaces?

Yes. You can define a strict schema for listworkspaces to ensure your agent only interacts with valid, authorized workspaces.

Get type-safe Comet ML metric extraction in Pydantic AI with strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Comet ML MCP to Pydantic AI

Create your Vinkius account to connect Comet ML to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Comet ML with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Comet ML metrics at runtime in Pydantic AI

Use `get_experiment_metrics` to enforce strict numeric bounds on your training data. Pydantic AI validates the returned floats against your schemas before your agent can use them. If Comet returns an unexpected null or an out-of-range value, the framework raises a validation error. You prevent corrupt run data from entering your evaluation pipeline.

Inspect experiment parameters with this MCP Server

This MCP Server exposes `get_experiment_params` to map API taxonomy types directly to Pydantic models. Your agent reads the exact run properties with zero risk of hallucinating field names. The runtime validation guarantees that every parameter type matches your expected Python classes. This keeps your model evaluation scripts completely type-safe.

Enforce strict project routing schemas

Call `list_projects` to ensure your agent never writes metrics to nonexistent or deprecated projects. Pydantic AI parses the structural extraction natively, rejecting any malformed project payloads. This strict check prevents your agent from making bad calls. You maintain a clean, verified ledger of your machine learning runs.

Setup guide

Set up Comet ML MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "comet-ml-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Comet ML tools.",
)

result = await agent.run("List recent Comet ML transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Comet ML. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Comet ML now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Comet ML MCP in Pydantic AI

Use the unified MCPToolset constructor with the Vinkius HTTP endpoint. Pass the toolset directly to your agent's toolsets argument.

The framework fails loudly. If get_experiment_metrics returns data that violates your schema, Pydantic AI raises a validation error immediately.

Yes. You can use the SSE or Streamable HTTP transport to pull experiment data like get_experiment in real time.

Yes. You can define a strict schema for list_workspaces to ensure your agent only interacts with valid, authorized workspaces.

Vinkius handles authentication at the proxy layer. Your workspace structures and training parameters are never exposed to the LLM without passing through type-safe filters.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript